Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 3096
    Prev
    Next
    INDEX
    Explanations

    references to anniversaries and significant celebratory events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تانيه
    -0.74
     gefragt
    -0.51
     setOpen
    -0.51
     InputDecoration
    -0.49
    bilisi
    -0.48
    ربای
    -0.48
     internetowa
    -0.48
    ódz
    -0.48
    topus
    -0.47
     ddelweddau
    -0.46
    POSITIVE LOGITS
     anniversary
    1.08
     anniversaries
    0.93
    versary
    0.87
     commemorating
    0.86
     aniversario
    0.85
     anniversaire
    0.85
     Anniversary
    0.84
     celebrating
    0.83
     celebration
    0.81
    anniversary
    0.81
    Activations Density 0.080%

    No Known Activations